AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Systematic Investigation of Sparse Perturbed Sharpness-Aware Minimization Optimizer

Peng Mi, Li Shen, Tianhe Ren, Yiyi Zhou, Tianshuo Xu, Xiaoshuai Sun, Tongliang Liu, Rongrong Ji, Dacheng Tao

TPAMI 2025 · Optimization › Implicit bias and generalization · approach: Sharpness-aware minimization theory · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
sparsify the perturbation to 50% (SSAM-F) instead of full SAM perturbationSAM, ResNet-18 · CIFAR100test accuracy: 81.03% -> 81.24%Improved
sparsify the perturbation to 50% (SSAM-F) instead of full SAMSAM, WideResNet28-10 · CIFAR100test accuracy: 84.20% -> 85.16%Improved
sparsify the perturbation to 50% (SSAM-D) instead of full SAMSAM, ResNet-18 · CIFAR100test accuracy: 81.03% -> 80.59%Hurt
raise sparsity from 50% to 99% (SSAM-D) (ablation)SSAM-D, ResNet-18 · CIFAR100test accuracy: 80.59% -> 79.61%Hurt
raise sparsity from 50% to 90% (SSAM-F) (ablation)SSAM-F, ResNet-50 · ImageNet-1ktest accuracy: 77.31% -> 76.74%Hurt
use Fisher-information top-k mask instead of random mask (ablation)SSAM-F, ResNet-50 · ImageNet-1ktest accuracy: 77.08% -> 77.31%Improved
drop flattest weights instead of sharpest weights (ablation)SSAM-D, ResNet-50 · ImageNet-1ktest accuracy: 76.68% -> 77.25%Improved
drop flattest weights instead of random drop (ablation)SSAM-D, ResNet-50 · ImageNet-1ktest accuracy: 77.08% -> 77.25%Improved
use unstructured instead of structured kernel mask (ablation)SSAM-F, ResNet-18 · CIFAR10 (50% sparsity)test accuracy: 96.73% -> 96.81%Improved
use explicit instead of implicit structured perturbation (ablation)SSAM-F, ResNet-18 · CIFAR10 (50% sparsity)test accuracy: 96.44% -> 96.73%Improved
use implicit N:M sparse perturbation (1:2) for ViTSSAM-F, ViT · CIFAR time per iterationtime per iteration: 4.10s -> 3.58sImproved
compute perturbation on 25% of data instead of 100% (ablation)SAM, ResNet-18 · CIFAR10test accuracy: 96.83% -> 96.55%Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy